We are looking for an experienced AI/LLM Python Developer to build a Retrieval-Augmented Generation (RAG) system. The system should be able to retrieve relevant data from custom sources (documents, APIs, or databases) and generate accurate responses using a Large Language Model. Key Responsibilities: Develop a RAG pipeline (retrieval + generation) Integrate LLM APIs (e.g., OpenAI, Claude) Work with vector databases (FAISS, Pinecone, etc.) Process and index documents (PDFs, text, structured data) Optimize prompts and response accuracy Required Skills: Strong Python experience Experience with LLM frameworks (LangChain, LlamaIndex) Familiarity with embeddings and vector search Experience building APIs (FastAPI/Flask) Understanding of prompt engineering Nice to Have: Experience with AWS/GCP Prior work on AI chatbots or knowledge systems